blk-mq: cleanup on all kinds of kobjects
cover blk-mq: cleanup on all kinds of kobjects
This patchset cleans up on kojects of request_queue.mq_kobj, sw queue's kobject and hw queue's kobject.
The 1st patch initialized kobject of request_queue and sw queue in blk_mq_init_allocated_queue(), so we can avoid to initialize these kobjects several times, and this patch fixes one kerne warning reported from Omar Sandoval.
The 2nd patch makes lifetime consitent between mq request queue/sw queue and their kobjects.
The 3rd patch makes lifetime consitent between hw queue and their kobjects.
The last patch is a followup of 3rd patch.
Thanks,
Ming
Ming Lei (4):
blk-mq: initialize mq kobjects in blk_mq_init_allocated_queue()
blk-mq: make lifetime consitent between q/ctx and its kobject
blk-mq: make lifetime consistent between hctx and its kobject
blk-mq: free hctx->cpumask in release handler of hctx's kobject
block/blk-mq-sysfs.c | 40 +++++++++++++++++++++++++--------------- block/blk-mq.c | 28 ++++++++++------------------ block/blk-mq.h | 2 ++ 3 files changed, 37 insertions(+), 33 deletions(-)
Signature · 1 line
2.7.4
PATCH 1/4 blk-mq: initialize mq kobjects in blk_mq_init_allocated_queue()
Both q->mq_kobj and sw queues' kobjects should have been initialized once, instead of doing that each add_disk context.
Also this patch removes clearing of ctx in blk_mq_init_cpu_queues() because percpu allocator fills zero to allocated variable.
This patch fixes one issue[1] reported from Omar.
[1] kernel wearning when doing unbind/bind on one scsi-mq device
[ 19.347924] kobject (ffff8800791ea0b8): tried to init an initialized object, something is seriously wrong. [ 19.349781] CPU: 1 PID: 84 Comm: kworker/u8:1 Not tainted 4.10.0-rc7-00210-g53f39eeaa263 #34 [ 19.350686] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-20161122_114906-anatol 04/01/2014 [ 19.350920] Workqueue: events_unbound async_run_entry_fn [ 19.350920] Call Trace: [ 19.350920] dump_stack+0x63/0x83 [ 19.350920] kobject_init+0x77/0x90 [ 19.350920] blk_mq_register_dev+0x40/0x130 [ 19.350920] blk_register_queue+0xb6/0x190 [ 19.350920] device_add_disk+0x1ec/0x4b0 [ 19.350920] sd_probe_async+0x10d/0x1c0 [sd_mod] [ 19.350920] async_run_entry_fn+0x48/0x150 [ 19.350920] process_one_work+0x1d0/0x480 [ 19.350920] worker_thread+0x48/0x4e0 [ 19.350920] kthread+0x101/0x140 [ 19.350920] ? process_one_work+0x480/0x480 [ 19.350920] ? kthread_create_on_node+0x60/0x60 [ 19.350920] ret_from_fork+0x2c/0x40
--- block/blk-mq-sysfs.c | 4 +--- block/blk-mq.c | 4 +++- block/blk-mq.h | 1 + 3 files changed, 5 insertions(+), 4 deletions(-)
block/blk-mq-sysfs.c +1 -3
@@ -277,7 +277,7 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)kobject_init (&hctx->kobj, &blk_mq_hw_ktype); } -static void blk_mq_sysfs_init (struct request_queue *q) +void blk_mq_sysfs_init (struct request_queue *q) {struct blk_mq_ctx *ctx;int cpu;
@@ -297,8 +297,6 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)blk_mq_disable_hotplug (); -blk_mq_sysfs_init (q); - ret =kobject_add (&q->mq_kobj,kobject_get (&dev->kobj),"%s" ,"mq" );if (ret <0 ) goto out;
block/blk-mq.c +3 -1
@@ -1941,7 +1941,6 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,struct blk_mq_ctx *__ctx =per_cpu_ptr (q->queue_ctx, i);struct blk_mq_hw_ctx *hctx; -memset (__ctx,0 ,sizeof (*__ctx)); __ctx->cpu = i;spin_lock_init (&__ctx->lock);INIT_LIST_HEAD (&__ctx->rq_list);
@@ -2248,6 +2247,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,if (!q->queue_ctx) goto err_exit; +/* init q->mq_kobj and sw queues' kobjects */ +blk_mq_sysfs_init (q); + q->queue_hw_ctx =kzalloc_node (nr_cpu_ids *sizeof (*(q->queue_hw_ctx)),GFP_KERNEL , set->numa_node);if (!q->queue_hw_ctx)
block/blk-mq.h +1 -0
@@ -77,6 +77,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,/* * sysfs helpers */ +extern void blk_mq_sysfs_init (struct request_queue *q);extern int blk_mq_sysfs_register (struct request_queue *q);extern void blk_mq_sysfs_unregister (struct request_queue *q);extern void blk_mq_hctx_kobj_init (struct blk_mq_hw_ctx *hctx);
Signature · 1 line
2.7.4
PATCH 2/4 blk-mq: make lifetime consitent between q/ctx and its kobject
In reply to Ming LeiCurrently from kobject view, both q->mq_kobj and ctx->kobj can be released during one cycle of blk_mq_register_dev() and blk_mq_unregister_dev(). Actually, sw queue's lifetime is same with its request queue's, which is covered by request_queue->kobj.
So we don't need to call kobject_put() for the two kinds of kobject in __blk_mq_unregister_dev(), instead we do that in release handler of request queue.
--- block/blk-mq-sysfs.c | 20 +++++++++++++------- block/blk-mq.c | 7 ++++++- block/blk-mq.h | 1 + 3 files changed, 20 insertions(+), 8 deletions(-)
block/blk-mq-sysfs.c +13 -7
@@ -242,15 +242,11 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)static void __blk_mq_unregister_dev (struct device *dev,struct request_queue *q) {struct blk_mq_hw_ctx *hctx; -struct blk_mq_ctx *ctx; -int i, j; +int i;queue_for_each_hw_ctx (q, hctx, i) {blk_mq_unregister_hctx (hctx); -hctx_for_each_ctx (hctx, ctx, j) -kobject_put (&ctx->kobj); -kobject_put (&hctx->kobj); }
@@ -258,8 +254,6 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)kobject_uevent (&q->mq_kobj,KOBJ_REMOVE );kobject_del (&q->mq_kobj); -kobject_put (&q->mq_kobj); -kobject_put (&dev->kobj); q->mq_sysfs_init_done = false;
@@ -277,6 +271,18 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)kobject_init (&hctx->kobj, &blk_mq_hw_ktype); } +void blk_mq_sysfs_deinit (struct request_queue *q) +{ +struct blk_mq_ctx *ctx; +int cpu; + +for_each_possible_cpu (cpu) { + ctx =per_cpu_ptr (q->queue_ctx, cpu); +kobject_put (&ctx->kobj); + } +kobject_put (&q->mq_kobj); +} +void blk_mq_sysfs_init (struct request_queue *q) {struct blk_mq_ctx *ctx;
block/blk-mq.c +6 -1
@@ -2160,7 +2160,12 @@ void blk_mq_release(struct request_queue *q)kfree (q->queue_hw_ctx); -/* ctx kobj stays in queue_ctx */ +/* +* release .mq_kobj and sw queue's kobject now because +* both share lifetime with request queue. +*/ +blk_mq_sysfs_deinit (q); +free_percpu (q->queue_ctx); }
block/blk-mq.h +1 -0
@@ -78,6 +78,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,* sysfs helpers */ extern void blk_mq_sysfs_init (struct request_queue *q); +extern void blk_mq_sysfs_deinit (struct request_queue *q);extern int blk_mq_sysfs_register (struct request_queue *q);extern void blk_mq_sysfs_unregister (struct request_queue *q);extern void blk_mq_hctx_kobj_init (struct blk_mq_hw_ctx *hctx);
Signature · 1 line
2.7.4
PATCH 3/4 blk-mq: make lifetime consistent between hctx and its kobject
In reply to Ming LeiThis patch removes kobject_put() over hctx in __blk_mq_unregister_dev(), and trys to keep lifetime consistent between hctx and hctx's kobject.
Now blk_mq_sysfs_register() and blk_mq_sysfs_unregister() become totally symmetrical, and kobject's refcounter drops to zero just when the hctx is freed.
--- block/blk-mq-sysfs.c | 15 ++++++++++----- block/blk-mq.c | 5 +---- 2 files changed, 11 insertions(+), 9 deletions(-)
block/blk-mq-sysfs.c +10 -5
@@ -17,6 +17,14 @@ static void blk_mq_sysfs_release(struct kobject *kobj) { } +static void blk_mq_hw_sysfs_release (struct kobject *kobj) +{ + struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx, + kobj); +kfree (hctx->ctxs); +kfree (hctx); +} +struct blk_mq_ctx_sysfs_entry {struct attribute attr;ssize_t (*show)(struct blk_mq_ctx *,char *);
@@ -200,7 +208,7 @@ static struct kobj_type blk_mq_ctx_ktype = {static struct kobj_type blk_mq_hw_ktype = { .sysfs_ops = &blk_mq_hw_sysfs_ops, .default_attrs = default_hw_ctx_attrs, - .release = blk_mq_sysfs_release, + .release = blk_mq_hw_sysfs_release, };static void blk_mq_unregister_hctx (struct blk_mq_hw_ctx *hctx)
@@ -244,12 +252,9 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)struct blk_mq_hw_ctx *hctx;int i; -queue_for_each_hw_ctx (q, hctx, i) { +queue_for_each_hw_ctx (q, hctx, i)blk_mq_unregister_hctx (hctx); -kobject_put (&hctx->kobj); - } -blk_mq_debugfs_unregister_hctxs (q);kobject_uevent (&q->mq_kobj,KOBJ_REMOVE );
block/blk-mq.c +1 -4
@@ -2152,8 +2152,7 @@ void blk_mq_release(struct request_queue *q)queue_for_each_hw_ctx (q, hctx, i) {if (!hctx)continue ; -kfree (hctx->ctxs); -kfree (hctx); +kobject_put (&hctx->kobj); } q->mq_map =NULL ;
@@ -2232,8 +2231,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,blk_mq_exit_hctx (q, set, hctx, j);free_cpumask_var (hctx->cpumask);kobject_put (&hctx->kobj); -kfree (hctx->ctxs); -kfree (hctx); hctxs[j] =NULL ; }
Signature · 1 line
2.7.4
PATCH 4/4 blk-mq: free hctx->cpumask in release handler of hctx's kobject
In reply to Ming LeiIt is obviously that hctx->cpumask is per hctx, and both share same lifetime, so this patch moves freeing of hctx->cpumask into release handler of hctx's kobject.
--- block/blk-mq-sysfs.c | 1 + block/blk-mq.c | 12 ------------ 2 files changed, 1 insertion(+), 12 deletions(-)
block/blk-mq-sysfs.c +1 -0
@@ -21,6 +21,7 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj) { struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj); +free_cpumask_var (hctx->cpumask);kfree (hctx->ctxs);kfree (hctx); }
block/blk-mq.c +0 -12
@@ -1851,16 +1851,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q, } } -static void blk_mq_free_hw_queues (struct request_queue *q, -struct blk_mq_tag_set *set) -{ -struct blk_mq_hw_ctx *hctx; -unsigned int i; - -queue_for_each_hw_ctx (q, hctx, i) -free_cpumask_var (hctx->cpumask); -} -static int blk_mq_init_hctx (struct request_queue *q,struct blk_mq_tag_set *set,struct blk_mq_hw_ctx *hctx,unsigned hctx_idx)
@@ -2229,7 +2219,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,if (hctx->tags)blk_mq_free_map_and_requests (set, j);blk_mq_exit_hctx (q, set, hctx, j); -free_cpumask_var (hctx->cpumask);kobject_put (&hctx->kobj); hctxs[j] =NULL ;
@@ -2342,7 +2331,6 @@ void blk_mq_free_queue(struct request_queue *q)blk_mq_del_queue_tag_set (q);blk_mq_exit_hw_queues (q, set, set->nr_hw_queues); -blk_mq_free_hw_queues (q, set); }/* Basically redo blk_mq_init_queue with queue frozen */
Signature · 1 line
2.7.4
Quoted 8 lines · Ming Lei
This patchset cleans up on kojects of request_queue.mq_kobj, sw queue's kobject and hw queue's kobject.
The 1st patch initialized kobject of
request_queueand sw queue inblk_mq_init_allocated_queue(), so we can avoid to initialize these kobjects several times, and this patch fixes one kerne warning reported from Omar Sandoval.
Quoted 7 lines
The 2nd patch makes lifetime consitent between mq request queue/sw queue and their kobjects.
The 3rd patch makes lifetime consitent between hw queue and their kobjects.
The last patch is a followup of 3rd patch.
These do indeed make the kobject warnings, and the resulting refcount warning, go away.
Quoted 8 lines · Ming Lei
This patchset cleans up on kojects of request_queue.mq_kobj, sw queue's kobject and hw queue's kobject.
The 1st patch initialized kobject of
request_queueand sw queue inblk_mq_init_allocated_queue(), so we can avoid to initialize these kobjects several times, and this patch fixes one kerne warning reported from Omar Sandoval.
Quoted 7 lines
The 2nd patch makes lifetime consitent between mq request queue/sw queue and their kobjects.
The 3rd patch makes lifetime consitent between hw queue and their kobjects.
The last patch is a followup of 3rd patch.
Thanks for looking into this, Ming. From a quick look, looks good to me. I'm going to queue it up for some testing, and hope that we can funnel this into 4.11 for the next pull request.
Signature · 1 line
Jens Axboe